INDEX

Explanations

repeated phrases and expressions indicating ongoing or long-term actions and commitments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eton

-0.15

 ÑģÐµÐ»

-0.15

Sle

-0.14

åĿĬ

-0.14

ected

-0.14

åĦĦ

-0.14

 voks

-0.14

ekil

-0.13

ãĥ³ãĤº

-0.13

ritten

-0.13

POSITIVE LOGITS

 since

0.18

Ã¢l

0.15

 decades

0.15

agraph

0.15

since

0.14

velle

0.14

 dating

0.14

decade

0.14

ARP

0.14

retty

0.14

Activations Density 0.093%

repeated phrases and expressions indicating ongoing or long-term actions and commitments

No Comments

No Known Activations